Management method and system based on indoor personnel positioning

Abstract

The invention discloses a management method and system based on indoor personnel positioning, and relates to the technical field of indoor enterprise management, and the method comprises the steps: carrying out the biological feature collection of indoor personnel, building a dynamic identity biological recognition model, and obtaining the biological feature data; comparing the acquired biological characteristic data with record information stored in a cloud end in a cloud computing technology, and acquiring position coordinates of peripheral personnel of the indoor personnel; a dangerous area is set, and indoor personnel positioning is managed. According to the invention, accurate positioning and intelligent early warning of indoor personnel are realized, the defects of incomplete biological characteristic acquisition, large positioning error, imperfect early warning mechanism and the like in the prior art are effectively solved, the comprehensiveness and accuracy of biological characteristic acquisition are improved, more accurate identity recognition of each person is ensured, the positioning precision is enhanced, and the positioning accuracy is improved. The positioning error is obviously reduced, the safety early warning mechanism is perfected, the intelligent early warning and safety disposal of the dangerous area are realized, and the intelligence and safety of management are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of indoor enterprise management, and in particular to a management method and system based on indoor personnel positioning. Background Art

[0002] In the context of the rapid development of the current society, intelligent management technology has been widely used in all walks of life, especially the positioning and management of indoor personnel has become a key requirement for ensuring safety and improving management efficiency in various scenarios. However, the existing positioning technology still has many deficiencies in accuracy, security and real-time performance, and cannot meet the high standards of modern management. Therefore, the present invention proposes a management method and system based on indoor personnel positioning to solve the problems existing in the existing technology and further improve the intelligent level of indoor personnel management.

[0003] When positioning people indoors, the existing technology often faces defects such as incomplete biometric collection, large positioning errors and imperfect early warning mechanisms, resulting in low management efficiency and increased safety hazards. The technical means of the present invention, that is, through the dynamic identity biometric recognition model combined with cloud computing and ultra-wideband positioning technology, can accurately locate and intelligently warn indoor personnel, effectively solving the defects of the existing technology. Summary of the invention

[0004] In view of the problems existing in the existing multi-source power grid information fusion and system based on the Internet of Things, the present invention is proposed.

[0005] Therefore, in order to solve the defects of the prior art such as incomplete biometric collection, large positioning error and imperfect early warning mechanism, the present invention adopts a dynamic identity biometric recognition model combined with cloud computing and ultra-wideband positioning technology.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a management method based on indoor personnel positioning, which includes collecting biometric features of indoor personnel, establishing a dynamic identity biometric recognition model, and using cloud computing technology to calculate the dynamic identity biometric recognition model to obtain biometric data;

[0008] Compare the acquired biometric data with the registered information stored in the cloud in cloud computing technology, use ultra-wideband positioning technology, combined with dynamic identity biometric recognition model, to complete the precise positioning of indoor personnel and obtain the location coordinates of the outsourced personnel of indoor personnel;

[0009] Set up danger zones, complete intelligent early warning safety disposal based on the coordinates of danger zones and peripheral personnel locations, and manage the positioning of indoor personnel.

[0010] As a preferred solution of the management method based on indoor personnel positioning described in the present invention, the biometric feature collection of indoor personnel includes collecting facial images, fingerprint images, iris images and voiceprint data of indoor personnel. The specific collection and calculation steps are as follows:

[0011] The facial image acquisition calculation formula is:

[0012]

[0013] Among them, g i Represents different feature extraction sub-functions, w i and b j represents the weight coefficient, k represents the kernel function, λ represents the regularization parameter, V f represents the facial image feature vector, F f represents the facial feature extraction function, I f represents a facial image, w i Represents the i-th feature extraction subfunction g i The weight coefficient, h j represents the jth feature extraction subfunction, Ω represents the facial image I f The domain of , k represents the kernel function, and x represents the integral variable;

[0014] The calculation formula for collecting the fingerprint image is:

[0015]

[0016] Among them, V fp represents the fingerprint feature vector, F fp represents the fingerprint feature extraction function, I fp represents the fingerprint image, α i Represents the i-th feature extraction subfunction u i The weight coefficient, p represents the weight coefficient for u i The number of features extracted by the sub-function feature, c j Represents the jth feature extraction subfunction v j The weight coefficient, v j represents the jth feature extraction subfunction, and q represents the function used for v j The number of features extracted by the sub-function feature extraction.

[0017] As a preferred solution of the management method based on indoor personnel positioning of the present invention, the collection calculation formula of the iris image is:

[0018]

[0019] Among them, V i represents the iris feature vector, F irepresents the iris feature extraction function, I i represents the iris image, d i Represents the i-th feature extraction subfunction e i The weight coefficient, e i represents the i-th feature extraction subfunction, r represents the number of features used for feature extraction, g i represents the i-th feature extraction subfunction, f i represents the i-th feature extraction subfunction, exp represents the exponential function, and log represents the logarithmic function;

[0020] The calculation formula for collecting the voiceprint data is:

[0021]

[0022] Among them, V s represents the voiceprint feature vector, F s represents the voiceprint feature extraction function, I s Indicates voiceprint data, h i represents the weight coefficient of the i-th feature extraction sub-function, sin represents the sine function, k i represents the coefficient in the sine function, cos represents the cosine function, l i represents the coefficient in the cosine function, and t represents the number of features extracted.

[0023] As a preferred solution of the management method based on indoor personnel positioning of the present invention, wherein: the establishment of a dynamic identity biometric recognition model includes fusing the collected biometric feature vectors to form a comprehensive feature vector V c , the specific fusion calculation formula is:

[0024] V c =α·V f +β·V fp +γ·V i +δ·V s

[0025] Among them, V c represents the comprehensive feature vector, α represents the facial feature vector V f The weight coefficient, V f represents the facial image feature vector, β represents the fingerprint feature vector V fp The weight coefficient, V fp represents the fingerprint feature vector, γ represents the iris feature vector V i The weight coefficient of δ represents the voiceprint feature vector V s The weight coefficient, V s represents the voiceprint feature vector;

[0026] The calculation of the dynamic identity biometric recognition model includes using encryption technology to calculate the comprehensive feature vector V c Encryption is performed to generate an encrypted feature vector, and the encrypted comprehensive feature vector is uploaded to the cloud computing platform to establish a dynamic identity biometric recognition model;

[0027] The comprehensive feature vector V c The specific calculation formula for encryption is:

[0028] V c，enc =Encrypt(V c , K)

[0029] Among them, V c，enc represents the encrypted feature vector, Encrypt represents the encryption function, V c represents the comprehensive feature vector, K represents the encryption key;

[0030] The uploading of the encrypted comprehensive feature vector to the cloud computing platform includes establishing a dynamic identity biometric recognition model using a cloud computing function, and the specific calculation formula is:

[0031] M bio =CloudCompute(V c，enc , D)

[0032] Among them, M bio represents the dynamic identity biometric recognition model, CloudCompute represents the cloud computing function, V c，enc represents the encrypted comprehensive feature vector, and D represents the training data set.

[0033] As a preferred solution of the management method based on indoor personnel positioning of the present invention, wherein: the acquisition of biometric data includes filtering the collected biometrics in combination with a dynamic identity biometric recognition model;

[0034] When the biometrics collection is incomplete, re-collection is required. The specific steps are as follows:

[0035] If the facial image does not meet the definition requirement, the biometric feature vector of the facial image is collected again. The specific calculation formula of the biometric feature vector of the facial image collected again is:

[0036] if clarity(I f )<θ,then I f ←re-capture

[0037] Where clarity represents the clarity detection function, θ represents the clarity threshold, and re-capture represents the re-capture function.

[0038] If the fingerprint image does not meet the definition requirement, the biometric feature vector of the fingerprint image is collected again. The specific calculation formula of the biometric feature vector of the fingerprint image collected again is:

[0039] if clarity(I fp )<θ fp , then I fp ←re-capture()

[0040] Among them, I fp represents the fingerprint image, clarity represents the clarity detection function, θ fp It represents the threshold of fingerprint image clarity, and re-capture() represents the re-capture function.

[0041] As a preferred solution of the management method based on indoor personnel positioning of the present invention, the accurate positioning of indoor personnel includes secondary fusion of the biometric features collected after filtering to form a secondary comprehensive feature vector V c，real , the specific calculation formula is:

[0042] V c，real =α·V f，real +β·V fp，real +γ·V i，real +δ·V s，real

[0043] Among them, α, β, γ and δ represent weight coefficients;

[0044] The secondary comprehensive eigenvector V c，real The record information M stored in the cloud in the cloud computing technology bio Compare and calculate the cosine degree between the two to determine the precise positioning of indoor personnel. The specific calculation formula is:

[0045]

[0046] Where D represents the cosine degree, dot_product represents the dot product of the vector, ||V c，real，enc || represents the modulus length of the encrypted real-time comprehensive feature vector, ||M bio || represents the modulus length of the dynamic identity biometric model stored in the cloud;

[0047] If the cosine degree D is less than the set threshold θ D , then the indoor personnel positioning is completed;

[0048] If the cosine degree D is greater than or equal to the set threshold θ D , the alarm mechanism is triggered.

[0049] As a preferred solution of the management method based on indoor personnel positioning described in the present invention, wherein: the safety disposal of completing the intelligent early warning includes calculating the alarm level according to the intelligent early warning mechanism to complete the management of indoor personnel positioning, and the specific calculation formula for calculating the alarm level is:

[0050] A=α1·D risk +α2·T exposure +α3·S critical

[0051] Among them, A represents the alarm level, D risk Indicates the risk level of the hazardous area, T exposure represents the exposure time, S critical It represents the status of key equipment in the area, and α1, α2 and α3 represent coefficients.

[0052] In a second aspect, an embodiment of the present invention provides a management system based on indoor personnel positioning, which includes: collecting biometric features of indoor personnel, establishing a dynamic identity biometric recognition model, calculating the dynamic identity biometric recognition model using cloud computing technology, and obtaining biometric feature data;

[0053] Compare the acquired biometric data with the registered information stored in the cloud in cloud computing technology, use ultra-wideband positioning technology, combined with dynamic identity biometric recognition model, to complete the precise positioning of indoor personnel and obtain the location coordinates of the outsourced personnel of indoor personnel;

[0054] Set up danger zones, complete intelligent early warning safety disposal based on the coordinates of danger zones and peripheral personnel locations, and manage the positioning of indoor personnel.

[0055] In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the processor executes the computer program, any step of the above-mentioned management method based on indoor personnel positioning is implemented.

[0056] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the above-mentioned management method based on indoor personnel positioning is implemented.

[0057] The beneficial effects of the present invention are as follows: the present invention realizes accurate positioning and intelligent early warning of indoor personnel through the combination of dynamic identity biometric recognition model, cloud computing technology and ultra-wideband positioning technology, effectively solves the defects of the prior art such as incomplete biometric collection, large positioning error and imperfect early warning mechanism, improves the comprehensiveness and accuracy of biometric collection, ensures more accurate identity recognition of each person, enhances positioning accuracy, significantly reduces positioning error through the integration of multiple technical means, improves the safety early warning mechanism, and realizes intelligent early warning and safe disposal of dangerous areas based on dynamic identity recognition and real-time positioning, thereby improving the intelligence and safety of management. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0059] Figure 1 A flowchart of a management method and system based on indoor personnel positioning is provided by one embodiment of the present invention.

[0060] Figure 2 A schematic diagram of a management method and system based on indoor personnel positioning provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0061] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0062] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0063] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0064] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0065] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0066] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0067] Example 1

[0068] Reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a management method based on indoor personnel positioning, comprising:

[0069] S1: Collect biometric features of people in the room, establish a dynamic identity biometric recognition model, use cloud computing technology to calculate the dynamic identity biometric recognition model, and obtain biometric data.

[0070] The biometric collection of indoor personnel includes collecting facial images, fingerprint images, iris images, and voiceprint data of indoor personnel. The specific collection and calculation steps are as follows:

[0071] The calculation formula for facial image acquisition is:

[0072]

[0073] Among them, g i Represents different feature extraction sub-functions, w i and b j represents the weight coefficient, k represents the kernel function, λ represents the regularization parameter, V f represents the facial image feature vector, Ff represents the facial feature extraction function, I f represents a facial image, w i Represents the i-th feature extraction subfunction g i The weight coefficient, h j represents the jth feature extraction subfunction, Ω represents the facial image I f The domain of , k represents the kernel function, and x represents the integral variable;

[0074] The calculation formula for fingerprint image acquisition is:

[0075]

[0076] Among them, V fb represents the fingerprint feature vector, F fp represents the fingerprint feature extraction function, I fp represents the fingerprint image, α i Represents the i-th feature extraction subfunction u i The weight coefficient, p represents the weight coefficient for u i The number of features extracted by the sub-function feature, c j Represents the jth feature extraction subfunction v j The weight coefficient, v j represents the jth feature extraction subfunction, and q represents the function used for v j The number of features extracted by the sub-function feature extraction.

[0077] S1.1: The calculation formula for collecting iris images is:

[0078]

[0079] Among them, V i represents the iris feature vector, F i represents the iris feature extraction function, I i represents the iris image, d i Represents the i-th feature extraction subfunction e i The weight coefficient, e i represents the i-th feature extraction subfunction, r represents the number of features used for feature extraction, g i represents the i-th feature extraction subfunction, f i represents the i-th feature extraction subfunction, exp represents the exponential function, and log represents the logarithmic function;

[0080] The calculation formula for voiceprint data collection is:

[0081]

[0082] Among them, V s represents the voiceprint feature vector, F srepresents the voiceprint feature extraction function, I s Indicates voiceprint data, h i represents the weight coefficient of the i-th feature extraction sub-function, sin represents the sine function, k i represents the coefficient in the sine function, cos represents the cosine function, l i represents the coefficient in the cosine function, and t represents the number of features extracted.

[0083] Furthermore, in the process of collecting biometric features of indoor personnel, the present invention comprehensively considers the comprehensiveness and accuracy of facial images, fingerprint images, iris images and voiceprint data. First, facial images are collected by a high-resolution camera, and feature vectors containing different feature sub-functions are extracted. In the specific steps, the number of feature extraction sub-functions is set to 5, and the weight coefficients are 0.2, 0.25, 0.15, 0.2 and 0.2 respectively. The kernel function adopts the Gaussian kernel function, and the regularization parameter is 0.01.

[0084] Secondly, the fingerprint image is collected by a dedicated fingerprint scanning device to extract the feature vector. In this process, the number of feature extraction sub-functions is 4, and the weight coefficients are 0.3, 0.2, 0.25 and 0.25 respectively. The number of features extracted by each sub-function is 20.

[0085] Then, the iris image is collected by an iris recognition device to extract the iris feature vector. In this step, the number of feature extraction subfunctions is 6, the weight coefficients are 0.18, 0.18, 0.16, 0.16, 0.16 and 0.16 respectively, and the number of features is set to 30.

[0086] Finally, the voiceprint data is collected through a high-sensitivity microphone to extract the voiceprint feature vector. In the voiceprint data processing, the number of feature extraction sub-functions is 3, and the weight coefficients are 0.35, 0.35 and 0.3 respectively. The number of features is set to 25, and the coefficients of the sine function and cosine function involved are 0.8 and 0.9 respectively.

[0087] S1.2: Establishing a dynamic identity biometric recognition model includes fusing the collected biometric feature vectors to form a comprehensive feature vector V c , the specific fusion calculation formula is:

[0088] V c =α·V f +α·V fp +γ·V i +δ·V s

[0089] Among them, V c represents the comprehensive feature vector, α represents the facial feature vector V f The weight coefficient, Vf represents the facial image feature vector, β represents the fingerprint feature vector V fb The weight coefficient, V fb represents the fingerprint feature vector, γ represents the iris feature vector V i The weight coefficient of δ represents the voiceprint feature vector V s The weight coefficient, V s represents the voiceprint feature vector;

[0090] The calculation of the dynamic identity biometric model includes using encryption technology to calculate the comprehensive feature vector V c Encryption is performed to generate an encrypted feature vector, and the encrypted comprehensive feature vector is uploaded to the cloud computing platform to establish a dynamic identity biometric recognition model;

[0091] For the comprehensive feature vector V c The specific calculation formula for encryption is:

[0092] V c，enc =Encrypt(V c , K)

[0093] Among them, V c，enc represents the encrypted feature vector, Encrypt represents the encryption function, V c represents the comprehensive feature vector, K represents the encryption key;

[0094] Uploading the encrypted comprehensive feature vector to the cloud computing platform includes using cloud computing functions to establish a dynamic identity biometric recognition model. The specific calculation formula is:

[0095] M bio =CloudCompute(V c，enc , D)

[0096] Among them, M bio represents the dynamic identity biometric recognition model, CloudCompute represents the cloud computing function, V c，enc represents the encrypted comprehensive feature vector, and D represents the training data set.

[0097] Furthermore, the process of establishing a dynamic identity biometric recognition model first requires the fusion of the collected facial feature vectors, fingerprint feature vectors, iris feature vectors, and voiceprint feature vectors. Specifically, the weight coefficient of the facial feature vector is set to 0.25, the weight coefficient of the fingerprint feature vector is 0.25, the weight coefficient of the iris feature vector is 0.25, and the weight coefficient of the voiceprint feature vector is 0.25. Through these weight coefficients, different biometric data are fused into a comprehensive feature vector.

[0098] Next, the comprehensive feature vector is encrypted. The AES encryption algorithm is used, and the encryption key length is 256 bits. After encryption, an encrypted feature vector is generated, and the length of the feature vector is 512 bits to ensure that the data is not leaked or tampered with during transmission.

[0099] Subsequently, the encrypted comprehensive feature vector is uploaded to the cloud computing platform. On the cloud computing platform, the encrypted feature vector is processed using cloud computing functions to establish a dynamic identity biometric recognition model. In order to train this model, the dataset used contains 100,000 sample data, including biometric data collected in various environments, to ensure the accuracy and robustness of the model.

[0100] In this way, the dynamic identity biometric recognition model can be updated and calculated in real time in the cloud, providing efficient and secure technical support for the positioning and management of indoor personnel. The dynamic identity biometric recognition model data is shown in Table 1 below:

[0101] Table 1 Dynamic identity biometric recognition model data table

[0102] project Numeric Facial feature vector weight coefficient 0.25 Fingerprint feature vector weight coefficient 0.25 Iris feature vector weight coefficient 0.25 Voiceprint feature vector weight coefficient 0.25 Encryption Algorithm AES Encryption key length 256 bits Encrypted feature vector length 512 bits Number of samples in the training dataset 100,000 Dataset Contents Biometric data in various environments

[0103] The table summarizes the key data used in establishing the dynamic identity biometric model, including that the weight coefficient of each type of biometric feature vector (face, fingerprint, iris, voiceprint) is 0.25, the encryption key length of the AES algorithm is 256 bits, and the encrypted feature vector length is 512 bits. The table also shows that the training data set contains 100,000 sample data, which comes from biometric collection in various environments to ensure the accuracy and robustness of the model.

[0104] S1.3: Acquiring biometric data includes filtering the collected biometrics in conjunction with a dynamic identity biometric recognition model;

[0105] When the biometrics collection is incomplete, re-collection is required. The specific steps are as follows:

[0106] If the facial image does not meet the definition requirement, the biometric feature vector of the facial image is collected again. The specific calculation formula of the biometric feature vector of the facial image collected again is:

[0107] if clarity(I f )<θ,then I f ←re-capture

[0108] Where clarity represents the clarity detection function, θ represents the clarity threshold, and re-capture represents the re-capture function.

[0109] If the fingerprint image does not meet the definition requirement, the biometric feature vector of the fingerprint image is collected again. The specific calculation formula of the biometric feature vector of the fingerprint image collected again is:

[0110] if clarity(I fp )<θ fp , then I fp ←re-capture()

[0111] Among them, I fp represents the fingerprint image, clarity represents the clarity detection function, θ fp It represents the threshold of fingerprint image clarity, and re-capture() represents the re-capture function.

[0112] Furthermore, when acquiring biometric data, the system will first filter the collected biometrics in combination with the dynamic identity biometric recognition model to ensure the accuracy and completeness of the data. If it is found that the collected biometric data is incomplete or does not meet the standards, the system will automatically trigger the re-collection process.

[0113] Specifically, when the clarity of a facial image is below a specified threshold, for example, below the 80% clarity standard, the system will re-capture the facial image. During this process, high-definition cameras are used to ensure that the image resolution reaches 1080p or above, ensuring the clarity and accuracy of facial features.

[0114] Similarly, for the collection of fingerprint images, the system will detect whether the clarity of the image meets the minimum standard, such as 90% clarity requirement. If it is detected that the fingerprint image does not meet the standard, the system will automatically trigger the re-collection process, using a high-precision fingerprint scanner to ensure that the resolution of the collected fingerprint image reaches 500dpi or above.

[0115] S2: Compare the acquired biometric data with the registered information stored in the cloud in the cloud computing technology, use ultra-wideband positioning technology, combined with a dynamic identity biometric recognition model, to complete the precise positioning of indoor personnel and obtain the location coordinates of the outsourced personnel of the indoor personnel.

[0116] Among them, the precise positioning of indoor personnel includes secondary fusion of the biometric features collected after filtering to form a secondary comprehensive feature vector V c，real , the specific calculation formula is:

[0117] V c，real =α·V f，real +β·V fp，real +γ·V i，real +δ·V s，real

[0118] Among them, α, β, γ and δ represent weight coefficients;

[0119] The secondary comprehensive eigenvector V c，real The record information stored in the cloud in cloud computing technology M bio Compare and calculate the cosine degree between the two to determine the precise positioning of indoor personnel. The specific calculation formula is:

[0120]

[0121] Where D represents the cosine degree, dot_product represents the dot product of the vector, ||V c，real，enc || represents the modulus length of the encrypted real-time comprehensive feature vector, ||M bio || represents the modulus length of the dynamic identity biometric model stored in the cloud;

[0122] If the cosine degree D is less than the set threshold θ D , then the indoor personnel positioning is completed;

[0123] If the cosine degree D is greater than or equal to the set threshold θ D , the alarm mechanism is triggered.

[0124] Preferably, in the process of completing the precise positioning of indoor personnel, the collected and filtered biometric data are first fused for a second time to form a secondary comprehensive feature vector. This process involves weight coefficients of different biometric vectors, among which the weight coefficients of facial features, fingerprint features, iris features and voiceprint features are 0.3, 0.3, 0.2 and 0.2 respectively. Such weight setting is based on the importance and stability of different features in the recognition process.

[0125] The secondary comprehensive feature vector is compared with the registered information stored in the cloud. In order to determine the accurate positioning of the person, the cosine degree between the two is calculated. If the calculated cosine degree is less than 0.1 (that is, the set threshold), the positioning is considered successful, and the location information of the indoor person is confirmed and recorded; if the cosine degree is greater than or equal to 0.1, the system triggers the alarm mechanism, indicating that there is a potential identity mismatch or data anomaly.

[0126] During the positioning process, ultra-wideband positioning technology provides accurate indoor location information with an error range of less than 10 centimeters. This high-precision positioning technology combined with a dynamic identity biometric model enables the system to obtain the specific location of indoor people in real time and accurately, especially the location coordinates of peripheral people, thereby providing reliable technical support for security management and personnel monitoring.

[0127] S3: Set up a danger zone, complete intelligent early warning safety disposal according to the coordinates of the danger zone and the location of peripheral personnel, and manage the positioning of indoor personnel.

[0128] Among them, completing the safety disposal of intelligent early warning includes calculating the alarm level according to the intelligent early warning mechanism and completing the management of indoor personnel positioning. The specific calculation formula for calculating the alarm level is:

[0129] A=α1·D risk +α2·T exposure +α3·S critical

[0130] Among them, A represents the alarm level, D risk Indicates the risk level of the hazardous area, T exposure represents the exposure time, S critical It represents the status of key equipment in the area, and α1, α2 and α3 represent coefficients.

[0131] Furthermore, in the process of completing the safety disposal of intelligent early warning, the danger zone is first set up, and the location coordinates of the outsourced personnel are compared with these danger zones. The system calculates the alarm level based on the specific risk level of the danger zone, the exposure time of the outsourced personnel in the area, and the status of the key equipment in the area.

[0132] Specifically, the risk levels of hazardous areas are divided into three levels: low, medium and high. Assuming that the risk level of a hazardous area is high, the exposure time of outsourced personnel in this area reaches 30 minutes, and the number of key equipment in this area is 5, the system uses these data to calculate the alarm level, where the weight coefficient of exposure time is set to 0.4, the weight coefficient of the risk level of the hazardous area is 0.4, and the weight coefficient of the key equipment situation is 0.2.

[0133] If the outsourced personnel are exposed in the high-risk area for more than 30 minutes and the key equipment in the area is operating normally, the calculated alarm level may reach 4 (out of 5), and the system will issue a high alarm and require immediate safety disposal measures. On the contrary, if the alarm level is lower (such as 1 or 2), the system will give corresponding safety recommendations to ensure that the safety management of indoor personnel is carried out in a timely and effective manner.

[0134] In a preferred embodiment, a management system based on indoor personnel positioning includes a collection module, which collects biometric features of indoor personnel, uses cloud computing technology to calculate a dynamic identity biometric recognition model, and obtains biometric data; a positioning module, which compares the acquired biometric data with the registered information stored in the cloud in the cloud computing technology to complete the precise positioning of indoor personnel; a management module, which sets a dangerous area, completes intelligent early warning safety disposal according to the coordinates of the dangerous area and the location of peripheral personnel, and manages the positioning of indoor personnel.

[0135] The above-mentioned unit modules may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to the above-mentioned modules.

[0136] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0137] In summary, the present invention realizes accurate positioning and intelligent early warning of indoor personnel through the combination of dynamic identity biometric recognition model, cloud computing technology and ultra-wideband positioning technology, effectively solves the defects of the prior art such as incomplete biometric collection, large positioning error and imperfect early warning mechanism, improves the comprehensiveness and accuracy of biometric collection, ensures more accurate identity recognition of each person, enhances positioning accuracy, significantly reduces positioning error through the integration of multiple technical means, improves the safety early warning mechanism, and realizes intelligent early warning and safe disposal of dangerous areas based on dynamic identity recognition and real-time positioning, thereby improving the intelligence and safety of management.

[0138] Example 2

[0139] Reference Figure 1 and Figure 2 , which is the second embodiment of the present invention, and this embodiment provides a management method based on indoor personnel positioning. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through simulation experiments.

[0140] During the experiment of the technical solution, the biometric features of the people in the room are first collected. Specifically, at the beginning of the experiment, a high-resolution camera is used to collect facial images to ensure that the image clarity is not less than 85%. At the same time, a fingerprint scanner and iris recognition device are used to collect fingerprint images and iris images to ensure that the resolution of the fingerprint image reaches 600dpi and the resolution of the iris image reaches 800x600 pixels. The sound features are collected through the voiceprint recognition system. The recorded voiceprint data length is 4 seconds and the sample collection frequency is 48kHz.

[0141] The collected biometric data is processed and fused, and the facial features, fingerprint features, iris features and voiceprint features are fused with a weight coefficient of 0.25 to form a comprehensive feature vector. Then, the comprehensive feature vector is encrypted using encryption technology to generate an encrypted feature vector with a length of 1024 bits, which is then uploaded to the cloud computing platform.

[0142] On the cloud computing platform, the encrypted feature vector is compared with the registered information stored in the cloud. In order to accurately locate indoor personnel, ultra-wideband positioning technology is used for positioning. The positioning error range is controlled within 8 cm. If the cosine degree of the comparison result is less than 0.15, the system considers the positioning accurate, otherwise the alarm mechanism is triggered.

[0143] The experiment further set up dangerous areas. For example, a medium-risk area was designated to contain 8 key equipment. In the experiment, if the outsourced personnel were exposed to the area for more than 45 minutes, the alarm level was calculated according to the set weight coefficient. If the calculated result was 5 or higher, the system would issue a high alarm and require immediate safety measures. If the alarm level was lower than the set threshold, safety recommendations were provided to ensure personnel safety. The experimental data parameters are shown in Table 2 below:

[0144] Table 2 Experimental data parameter table

[0145] Experimental Project data Facial image clarity Not less than 85% Fingerprint image resolution 600dpi Iris image resolution 800x600 pixels Voiceprint data length 4 seconds Voiceprint sampling frequency 48kHz Feature fusion weight 0.25 Encrypted feature vector length 1024 bits Positioning error range Keep within 8 cm Cosine Degree Threshold Less than 0.15 Number of critical equipment in hazardous areas 8 units Exposure time threshold More than 45 minutes High Alert Level Threshold The result is 5 or higher

[0146] The table shows the specific data parameters used in the experiment, including facial image clarity, fingerprint image and iris image resolution, voiceprint data length and sampling frequency, feature fusion weight coefficient and encrypted feature vector length, in addition, it also includes the positioning error range, cosine threshold, number of key equipment in the danger zone, exposure time threshold and high alarm level threshold. These data parameters provide a detailed basis for the experimental setting and effect evaluation of the technical solution. The comparison between the present invention and the prior art is shown in Table 3 below:

[0147] Table 3 Comparison between the present invention and the prior art

[0148]

[0149] The main advantages of the technical solution of the present invention over the prior art are its innovation and improvement in biometric feature collection, data fusion, security, positioning accuracy and alarm management.

[0150] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A management method based on indoor personnel positioning, characterized in that: include, Collect biometric features of indoor personnel, establish a dynamic identity biometric recognition model, use cloud computing technology to calculate the dynamic identity biometric recognition model, and obtain biometric data; Compare the acquired biometric data with the registered information stored in the cloud in the cloud computing technology, use ultra-wideband positioning technology, combined with the dynamic identity biometric recognition model, to complete the precise positioning of indoor personnel and obtain the location coordinates of the outsourced personnel of the indoor personnel; Set up danger zones, complete intelligent early warning safety disposal based on the coordinates of danger zones and peripheral personnel locations, and manage the positioning of indoor personnel.

2. The management method based on indoor personnel positioning according to claim 1, characterized in that: The biometric collection of indoor personnel includes collecting facial images, fingerprint images, iris images and voiceprint data of indoor personnel. The specific collection and calculation steps are as follows: The facial image acquisition calculation formula is: Among them, g i Represents different feature extraction sub-functions, w i and b j represents the weight coefficient, k represents the kernel function, λ represents the regularization parameter, V f represents the facial image feature vector, F f represents the facial feature extraction function, I f represents a facial image, w i Represents the i-th feature extraction subfunction g i The weight coefficient, h j represents the jth feature extraction subfunction, Ω represents the facial image I f The domain of , k represents the kernel function, and x represents the integral variable; The calculation formula for collecting the fingerprint image is: Among them, V fp represents the fingerprint feature vector, F fp represents the fingerprint feature extraction function, I fp represents the fingerprint image, α i Represents the i-th feature extraction subfunction u i The weight coefficient, p represents the weight coefficient for u i The number of features extracted by the sub-function feature, c j Represents the jth feature extraction subfunction v j The weight coefficient, v j represents the jth feature extraction subfunction, and q represents the function used for v j The number of features extracted by the sub-function feature extraction.

3. The management method based on indoor personnel positioning according to claim 2, characterized in that: The acquisition calculation formula of the iris image is: Among them, V i represents the iris feature vector, F i represents the iris feature extraction function, I i represents the iris image, d i Represents the i-th feature extraction subfunction e i The weight coefficient, e i represents the i-th feature extraction subfunction, r represents the number of features used for feature extraction, g i represents the i-th feature extraction subfunction, f i represents the i-th feature extraction subfunction, exp represents the exponential function, and log represents the logarithmic function; The calculation formula for collecting the voiceprint data is: Among them, V s represents the voiceprint feature vector, F s represents the voiceprint feature extraction function, I s Indicates voiceprint data, h i represents the weight coefficient of the i-th feature extraction sub-function, sin represents the sine function, k i represents the coefficient in the sine function, cos represents the cosine function, l i represents the coefficient in the cosine function, and t represents the number of features extracted.

4. The management method based on indoor personnel positioning according to claim 3, characterized in that: The establishment of a dynamic identity biometric recognition model includes fusing the collected biometric feature vectors to form a comprehensive feature vector V c , the specific fusion calculation formula is: V c =α·V f +α·V fp +γ·V i +δ·V s Among them, V c represents the comprehensive feature vector, α represents the facial feature vector V f The weight coefficient, V f represents the facial image feature vector, β represents the fingerprint feature vector V fp The weight coefficient, V fp represents the fingerprint feature vector, γ represents the iris feature vector V i The weight coefficient of δ represents the voiceprint feature vector V s The weight coefficient, V s represents the voiceprint feature vector; The calculation of the dynamic identity biometric recognition model includes using encryption technology to calculate the comprehensive feature vector V c Encryption is performed to generate an encrypted feature vector, and the encrypted comprehensive feature vector is uploaded to the cloud computing platform to establish a dynamic identity biometric recognition model; The comprehensive feature vector V c The specific calculation formula for encryption is: V c，enc =Encrypt(V c (K) Among them, V c，enc represents the encrypted feature vector, Encrypt represents the encryption function, V c represents the comprehensive feature vector, K represents the encryption key; The uploading of the encrypted comprehensive feature vector to the cloud computing platform includes establishing a dynamic identity biometric recognition model using a cloud computing function, and the specific calculation formula is: M bio =CloudCompute(V c，enc ,D) Among them, M bio represents the dynamic identity biometric recognition model, CloudCompute represents the cloud computing function, V c，enc represents the encrypted comprehensive feature vector, and D represents the training data set.

5. The management method based on indoor personnel positioning according to claim 4, characterized in that: The acquiring of biometric data includes filtering the collected biometrics in combination with a dynamic identity biometric recognition model; When the biometrics collection is incomplete, re-collection is required. The specific steps are as follows: If the facial image does not meet the definition requirement, the biometric feature vector of the facial image is collected again. The specific calculation formula of the biometric feature vector of the facial image collected again is: if clarity(I f )<θ,then I f ←re-capture Where clarity represents the clarity detection function, θ represents the clarity threshold, and re-capture represents the re-capture function. If the fingerprint image does not meet the definition requirement, the biometric feature vector of the fingerprint image is collected again. The specific calculation formula of the biometric feature vector of the fingerprint image collected again is: if clarity(I fp )<θ fp ,then I fp ←re-capture() Among them, I fp represents the fingerprint image, clarity represents the clarity detection function, θ fp It represents the threshold of fingerprint image clarity, and re-capture() represents the re-capture function.

6. The management method based on indoor personnel positioning according to claim 5, characterized in that: The precise positioning of indoor personnel includes secondary fusion of the biometric features collected after filtering to form a secondary comprehensive feature vector V c，real , the specific calculation formula is: V c，real =α·V f，real +β·V fp，real +γ·V i，real +δ·V s，real Among them, α, β, γ and δ represent weight coefficients; The secondary comprehensive eigenvector V c，real The record information M stored in the cloud in the cloud computing technology bio Compare and calculate the cosine degree between the two to determine the precise positioning of indoor personnel. The specific calculation formula is: Where D represents the cosine degree, dot_product represents the dot product of the vector, ||V c，real，enc || represents the modulus length of the encrypted real-time comprehensive feature vector, ||M bio || represents the modulus length of the dynamic identity biometric model stored in the cloud; If the cosine degree D is less than the set threshold θ D , then the indoor personnel positioning is completed; If the cosine degree D is greater than or equal to the set threshold θ D , the alarm mechanism is triggered.

7. The management method based on indoor personnel positioning according to claim 6, characterized in that: The safety disposal of completing the intelligent early warning includes calculating the alarm level according to the intelligent early warning mechanism and completing the management of the indoor personnel positioning. The specific calculation formula for calculating the alarm level is: A=α1·D risk +α2·T exposure +α3·S critical Among them, A represents the alarm level, D risk Indicates the risk level of the hazardous area, T exposure represents the exposure time, S critical It represents the status of key equipment in the area, and α1, α2 and α3 represent coefficients.

8. A management system based on indoor personnel positioning, based on the management method based on indoor personnel positioning according to any one of claims 1 to 7, characterized in that: include, The collection module collects biometric features of people in the room, calculates the dynamic identity biometric recognition model using cloud computing technology, and obtains biometric data; The positioning module compares the acquired biometric data with the registered information stored in the cloud in the cloud computing technology to accurately locate the indoor personnel; The management module sets up dangerous areas, completes intelligent early warning safety disposal according to the coordinates of dangerous areas and peripheral personnel positions, and manages the positioning of indoor personnel.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the management method based on indoor personnel positioning according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the management method based on indoor personnel positioning according to any one of claims 1 to 7 are implemented.

Images